Personal training with physical activity monitoring device

• US 8,951,165 B2
• Filed: 03/05/2013
• Issued: 02/10/2015
• Est. Priority Date: 03/05/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Morris, Daniel, Kelner, Ilya, Shariff, Farah, Tom, Dennis, Saponas, T. Scott, Guillory, Andrew
• Primary Examiner(s): Suhol, Dmitry
• Assistant Examiner(s): YEN, JASON TAHAI
• Application Number:
  US13/785,322
• Publication Number:
  US 20140257535A1
• Time in Patent Office: 707 Days
• Field of Search: None
• US Class Current: 482/8
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/1123 Discriminating type of movement, e.g. walking or running A61B5/1116, A61B5/112 take precedence
• CPC Class Codes: A61B 5/681 Wristwatch-type devices
• CPC Class Codes: A61B 5/6824 Arm or wrist
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: A63B 2024/0068 Comparison to target or threshold, previous performance or not real time comparison to other individuals
• CPC Class Codes: A63B 2071/0663 worn on the wrist, e.g. wrist bands
• CPC Class Codes: A63B 2220/17 Counting, e.g. counting periodical movements, revolutions or cycles, or including further data processing to determine distances or speed
• CPC Class Codes: A63B 24/0062 Monitoring athletic performances, e.g. for determining the work of a user on an exercise apparatus, the completed jogging or cycling distance
• CPC Class Codes: A63B 24/0075 Means for generating exercise programs or schemes, e.g. computerized virtual trainer, e.g. using expert databases
• CPC Class Codes: G16H 20/30 relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising

Abstract

A physical activity monitoring device receives a workout regimen including a plurality of exercises. For each of the plurality of exercises, the physical activity monitoring device indicates that exercise to a user and measures physical activity attributes of the user. The physical activity monitoring device outputs information regarding the user'"'"'s progress towards completion of that exercise based on the physical activity attributes.

Claims

1. A method of physically training a user, the method comprising;

at a physical activity monitoring device including a sensor array including an accelerometer, receiving a workout regimen including a plurality of exercises;

for each of the plurality of exercises;

at the physical activity monitoring device, indicating the exercise to the user;

with the physical activity monitoring device worn by the user, measuring physical activity attributes of the user;

automatically determining time intervals where the user is actively engaged in the exercise based on the physical activity attributes at least in part by;

acquiring signal information with the sensor array that is representative of the physical activity attributes of the user;

dividing the signal information into overlapping segments;

identifying predetermined signal characteristics for each overlapping segment; and

analyzing the predetermined signal characteristics for each overlapping segment using a supervised classifier trained to recognize if the user is actively engaged in the exercise during the overlapping segment;

outputting information regarding the user'"'"'s progress towards completion of the exercise based on the physical activity attributes; and

if the workout regimen has not been completed, indicating a next exercise to the user.

2. The method of claim 1, further comprising:

indicating to the user that an exercise has been completed.

3. The method of claim 1, further comprising:

calculating one or more current biometric markers for the user performing the plurality of exercises.

4. The method of claim 3, further comprising:

indicating to the user one or more current biometric markers.

5. The method of claim 4, where the one or more biometric markers include an amount of calories burned by the user performing the one or more physical activities.

6. The method of claim 1, where the supervised classifier includes a support vector machine, and where analyzing the predetermined signal characteristics further includes:

training the support vector machine with data collected from a plurality of users during time intervals where the users were engaged in a plurality of types of exercises;

generating a set of transformation vectors and a weight vector representative of a user engaged in a type of exercise;

multiplying the predetermined signal characteristics by the set of transformation vectors and weight vector to obtain a plurality of multiplication products;

comparing the multiplication products to data sets representative of each of a plurality of exercises where the data sets have been predetermined through machine learning; and

classifying overlapping segments as representative of a type of exercise.

7. The method of claim 6, where the physical activity monitoring device further includes an aggregator configured to determine a time interval defined by a plurality of the classified overlapping segments where the user is likely to be actively engaged in an exercise.

8. The method of claim 1, further comprising:

for a repetitive exercise;

indicating to the user a target number of repetitions of an exercise to be performed;

determining a number of repetitions of the repetitive exercise performed by the user with a process that reduces a dimensionality of signals received from the sensor array.

9. The method of claim 8, where the number of repetitions is determined through a counting method that includes:

counting a number of peaks of the dimensionally reduced signal; and

outputting the number of peaks.

10. The method of claim 9, where the counting method further includes:

determining a set of candidate peaks;

filtering the candidate peaks using local period estimates;

filtering the candidate peaks using amplitude statistics; and

outputting the number of peaks.

11. The method of claim 10, where the counting method further includes:

determining a set of candidate valleys;

filtering the candidate valleys using local period estimates;

filtering the candidate valleys using amplitude statistics;

counting a number of valleys of the dimensionally reduced signal;

comparing the number of valleys to the number of peaks; and

designating the greater of the number of valleys and the number of peaks as a number of repetitions; and

outputting the number of repetitions.

12. The method of claim 11, where the counting method further includes:

determining that the user has stopped performing a repetitive exercise based on the physical activity attributes;

comparing the number of repetitions determined by the counting method to the target number of repetitions;

indicating that the user has completed the repetitive exercise when the number of repetitions determined by the counting method is within two of the target number.

13. A physical activity monitoring device, comprising:

a communication subsystem configured to receive a workout regimen including a plurality of exercises;

a display subsystem configured to, for each of the plurality of exercises, indicate that exercise to a user;

a sensor array including one or more sensors configured to measure physical activity attributes of the user;

a controller trained with a machine learning process to automatically determine time intervals where the user is actively engaged in that exercise based on predetermined signal characteristics for overlapping segments of signal information from the sensor array, and to automatically determine the user'"'"'s progress towards completion of that exercise based on the predetermined signal characteristics physical activity attributes; and

a reporter configured to output information regarding the user'"'"'s progress towards completion of that exercise.

14. The physical activity monitoring device of claim 13, further comprising a supervised classifier.

15. The physical activity monitoring device of claim 14, where the supervised classifier includes a support vector machine.

16. A method of physically training a user with a physical activity monitoring device worn by the user, the physical activity monitoring device including a sensor array including one or more sensors, the method comprising:

at the physical activity monitoring device, receiving a workout regimen including a plurality of exercises;

for each of the plurality of exercises;

at the physical activity monitoring device, indicating the exercise to the user;

with the sensor array, measuring physical activity attributes of the user;

at the physical activity monitoring device, automatically determining time intervals where the user is actively engaged in the exercise based on predetermined signal characteristics for overlapping segments of signal information from the sensor array;

at the physical activity monitoring device, automatically determining the user'"'"'s progress towards completion of the exercise based on the predetermined signal characteristics;

outputting information regarding the user'"'"'s progress towards completion of the exercise; and

if the workout regimen has not been completed, indicating a next exercise to the user.